A Media Frame Analysis (2023–2025)
This report analyzes Croatian web media coverage of Generative AI in education from 2023 to 2025. Using computational frame analysis and natural language processing, we examine how media narratives have evolved from initial panic to gradual integration.
The release of ChatGPT in November 2022 triggered a global conversation about artificial intelligence in education. Croatia, like many countries, witnessed intense media debate about the implications of generative AI for students, teachers, and educational institutions.
This analysis addresses four core questions:
Our analysis draws on:
# Load the pre-processed data
raw_data <- read.xlsx("./dta.xlsx")
cat("Dataset loaded successfully\n")Dataset loaded successfullycat("Total articles:", format(nrow(raw_data), big.mark = ","), "\n")Total articles: 4,424 cat("Columns:", ncol(raw_data), "\n")Columns: 48 # Validate and clean data
validated_data <- raw_data %>%
filter(!is.na(FULL_TEXT) & !is.na(TITLE))
# Parse dates
clean_data <- validated_data %>%
mutate(
DATE = as.Date(DATE),
year = year(DATE),
month = month(DATE),
year_month = floor_date(DATE, "month"),
week = floor_date(DATE, "week"),
quarter = quarter(DATE),
word_count = str_count(FULL_TEXT, "\\S+"),
article_id = row_number()
) %>%
filter(!is.na(DATE)) %>%
distinct(TITLE, DATE, .keep_all = TRUE) %>%
arrange(DATE)
# Day of week
clean_data$day_of_week <- wday(clean_data$DATE, label = TRUE, abbr = FALSE)
cat("Articles after cleaning:", format(nrow(clean_data), big.mark = ","), "\n")Articles after cleaning: 3,873 cat("Date range:", as.character(min(clean_data$DATE)), "to", as.character(max(clean_data$DATE)), "\n")Date range: 2021-01-01 to 2024-07-04 We developed Croatian-language dictionaries for eight interpretive frames:
frame_dictionaries <- list(
THREAT = c(
"prijetnja", "opasnost", "opasno", "rizik", "rizično",
"varanje", "varati", "prevara", "plagijat", "plagiranje",
"prepisivanje", "zabrana", "zabraniti", "zabranjeno",
"uništiti", "uništava", "smrt", "kraj", "propast",
"kriza", "alarm", "upozorenje", "šteta", "štetno",
"strah", "bojati", "panika"
),
OPPORTUNITY = c(
"alat", "sredstvo", "pomoć", "pomoćnik", "asistent",
"prilika", "mogućnost", "potencijal", "prednost", "korist",
"poboljšati", "poboljšanje", "unaprijediti", "napredak",
"učinkovit", "učinkovitost", "efikasan", "produktivnost",
"budućnost", "inovacija", "inovativan", "revolucija",
"moderan", "modernizacija", "transformacija",
"uspjeh", "uspješno", "izvrsno"
),
REGULATION = c(
"pravilnik", "pravilo", "propisi", "regulativa",
"smjernice", "upute", "protokol",
"zakon", "zakonski", "pravni",
"ministarstvo", "ministar", "vlada",
"dopušteno", "dopuštenje", "dozvola",
"primjena", "provedba", "implementacija",
"odluka", "mjera"
),
DISRUPTION = c(
"promjena", "promijeniti", "transformacija", "preobrazba",
"prilagodba", "prilagoditi", "adaptacija",
"neizbježno", "nezaustavljivo",
"revolucija", "prekretnica", "nova era", "novi način",
"evolucija", "disrupcija"
),
REPLACEMENT = c(
"zamjena", "zamijeniti", "zamjenjuje", "istisnuti",
"gubitak posla", "nepotreban", "suvišan", "zastario",
"automatizacija", "automatizirano",
"nadmašiti", "bolji od čovjeka"
),
QUALITY = c(
"halucinacija", "halucinacije", "greška", "greške",
"netočno", "netočnost", "pogrešno",
"pouzdanost", "pouzdan", "nepouzdan",
"provjera", "provjeriti", "verifikacija",
"kvaliteta", "kritički", "kritičko mišljenje"
),
EQUITY = c(
"nejednakost", "nejednako", "jaz", "razlika",
"pristup", "pristupačnost", "dostupnost",
"digitalni jaz", "siromašan", "socioekonomski",
"pravednost", "pravedno", "nepravedno"
),
COMPETENCE = c(
"vještine", "vještina", "kompetencije",
"sposobnost", "pismenost", "digitalna pismenost",
"kritičko mišljenje", "analitičko mišljenje",
"učiti", "obrazovanje", "edukacija", "usavršavanje"
)
)
# Actor dictionaries
actor_dictionaries <- list(
STUDENTS = c("student", "studenti", "učenik", "učenici", "đak", "maturant", "brucoš"),
TEACHERS = c("učitelj", "učitelji", "nastavnik", "profesor", "profesori", "predavač", "mentor"),
ADMINISTRATORS = c("ravnatelj", "dekan", "rektor", "prorektor", "voditelj"),
INSTITUTIONS = c("škola", "škole", "fakultet", "sveučilište", "ministarstvo", "carnet"),
TECH_COMPANIES = c("openai", "microsoft", "google", "chatgpt", "gpt", "gemini", "copilot"),
EXPERTS = c("stručnjak", "ekspert", "znanstvenik", "istraživač", "analitičar"),
POLICY_MAKERS = c("ministar", "zastupnik", "premijer", "vlada", "sabor")
)
# Sentiment dictionaries
sentiment_positive <- c(
"dobar", "dobro", "odličan", "sjajan", "izvrstan", "fantastičan",
"pozitivan", "uspješan", "uspjeh", "napredak", "poboljšanje",
"zadovoljan", "optimizam", "nada", "kvalitetan", "koristan"
)
sentiment_negative <- c(
"loš", "loše", "negativan", "grozan", "užasan", "katastrofa",
"problem", "neuspjeh", "propast", "pogoršanje",
"nezadovoljan", "razočaran", "pesimizam", "strah",
"nekvalitetan", "beskoristan"
)
cat("Frame dictionaries created:", length(frame_dictionaries), "frames\n")Frame dictionaries created: 8 framescat("Actor dictionaries created:", length(actor_dictionaries), "actor types\n")Actor dictionaries created: 7 actor types# Function to detect frames
detect_frames <- function(text, dictionaries) {
if (is.na(text)) return(setNames(rep(0, length(dictionaries)), names(dictionaries)))
text_lower <- str_to_lower(text)
sapply(names(dictionaries), function(frame_name) {
pattern <- paste0("\\b(", paste(dictionaries[[frame_name]], collapse = "|"), ")")
sum(str_count(text_lower, pattern))
})
}
detect_frame_presence <- function(text, dictionaries) {
if (is.na(text)) return(setNames(rep(FALSE, length(dictionaries)), names(dictionaries)))
text_lower <- str_to_lower(text)
sapply(names(dictionaries), function(frame_name) {
pattern <- paste0("\\b(", paste(dictionaries[[frame_name]], collapse = "|"), ")")
str_detect(text_lower, pattern)
})
}
# Apply frame analysis (with progress indicator)
message("Applying frame analysis...")
frame_results <- lapply(seq_len(nrow(clean_data)), function(i) {
combined_text <- paste(clean_data$TITLE[i], clean_data$FULL_TEXT[i], sep = " ")
frame_counts <- detect_frames(combined_text, frame_dictionaries)
frame_presence <- detect_frame_presence(combined_text, frame_dictionaries)
actor_counts <- detect_frames(combined_text, actor_dictionaries)
actor_presence <- detect_frame_presence(combined_text, actor_dictionaries)
# Sentiment
text_lower <- str_to_lower(combined_text)
pos_count <- sum(str_count(text_lower, paste0("\\b(", paste(sentiment_positive, collapse = "|"), ")")))
neg_count <- sum(str_count(text_lower, paste0("\\b(", paste(sentiment_negative, collapse = "|"), ")")))
c(
setNames(frame_counts, paste0("frame_", names(frame_counts), "_count")),
setNames(frame_presence, paste0("frame_", names(frame_presence), "_present")),
setNames(actor_counts, paste0("actor_", names(actor_counts), "_count")),
setNames(actor_presence, paste0("actor_", names(actor_presence), "_present")),
sentiment_POSITIVE_count = pos_count,
sentiment_NEGATIVE_count = neg_count
)
})
frame_df <- bind_rows(lapply(frame_results, as.data.frame.list))
clean_data <- bind_cols(clean_data, frame_df)
# Calculate derived metrics
clean_data <- clean_data %>%
mutate(
dominant_frame = apply(
select(., starts_with("frame_") & ends_with("_count") & !contains("frame_count")), 1,
function(x) {
frame_names <- c("THREAT", "OPPORTUNITY", "REGULATION", "DISRUPTION",
"REPLACEMENT", "QUALITY", "EQUITY", "COMPETENCE")
if (all(x == 0)) return("NONE")
frame_names[which.max(x)]
}
),
frame_intensity = rowSums(select(., starts_with("frame_") & ends_with("_count") & !contains("frame_count"))),
frame_count = rowSums(select(., starts_with("frame_") & ends_with("_present"))),
sentiment_score = sentiment_POSITIVE_count - sentiment_NEGATIVE_count,
sentiment_category = case_when(
sentiment_score > 2 ~ "Positive",
sentiment_score < -2 ~ "Negative",
TRUE ~ "Neutral"
),
primary_actor = apply(
select(., starts_with("actor_") & ends_with("_count")), 1,
function(x) {
actor_names <- c("STUDENTS", "TEACHERS", "ADMINISTRATORS", "INSTITUTIONS",
"TECH_COMPANIES", "EXPERTS", "POLICY_MAKERS")
if (all(x == 0)) return("NONE")
actor_names[which.max(x)]
}
),
narrative_phase = case_when(
DATE < as.Date("2023-06-01") ~ "Phase 1: Emergence",
DATE < as.Date("2024-01-01") ~ "Phase 2: Debate",
DATE < as.Date("2024-09-01") ~ "Phase 3: Integration",
TRUE ~ "Phase 4: Normalization"
)
)
cat("Frame analysis complete.\n")Frame analysis complete.cat("Articles with at least one frame:", sum(clean_data$frame_count > 0), "\n")Articles with at least one frame: 3154 summary_stats <- tibble(
Metric = c(
"Total Articles",
"Date Range",
"Unique Sources",
"Total Words Analyzed",
"Mean Article Length (words)",
"Articles with Frame Detected"
),
Value = c(
format(nrow(clean_data), big.mark = ","),
paste(min(clean_data$DATE), "to", max(clean_data$DATE)),
format(n_distinct(clean_data$FROM), big.mark = ","),
format(sum(clean_data$word_count, na.rm = TRUE), big.mark = ","),
format(round(mean(clean_data$word_count, na.rm = TRUE)), big.mark = ","),
paste0(format(sum(clean_data$frame_count > 0), big.mark = ","),
" (", round(mean(clean_data$frame_count > 0) * 100, 1), "%)")
)
)
kable(summary_stats, align = c("l", "r")) %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)| Metric | Value |
|---|---|
| Total Articles | 3,873 |
| Date Range | 2021-01-01 to 2024-07-04 |
| Unique Sources | 512 |
| Total Words Analyzed | 1,483,958 |
| Mean Article Length (words) | 383 |
| Articles with Frame Detected | 3,154 (81.4%) |
monthly_stats <- clean_data %>%
group_by(year_month) %>%
summarise(
n_articles = n(),
prop_THREAT = mean(frame_THREAT_present, na.rm = TRUE),
prop_OPPORTUNITY = mean(frame_OPPORTUNITY_present, na.rm = TRUE),
prop_REGULATION = mean(frame_REGULATION_present, na.rm = TRUE),
mean_sentiment = mean(sentiment_score, na.rm = TRUE),
.groups = "drop"
)
ggplot(monthly_stats, aes(x = year_month, y = n_articles)) +
geom_col(fill = "#2c7bb6", alpha = 0.8) +
geom_smooth(method = "loess", se = TRUE, color = "#d7191c", linewidth = 1.2) +
scale_x_date(date_breaks = "3 months", date_labels = "%b\n%Y") +
labs(
title = "Media Coverage of AI in Croatian Education",
subtitle = "Monthly article count with trend line",
x = NULL,
y = "Number of Articles"
)
dow_stats <- clean_data %>%
filter(!is.na(day_of_week)) %>%
count(day_of_week) %>%
mutate(percentage = n / sum(n) * 100)
ggplot(dow_stats, aes(x = day_of_week, y = n)) +
geom_col(fill = "#2c7bb6", alpha = 0.8) +
geom_text(aes(label = paste0(round(percentage, 1), "%")), vjust = -0.5, size = 3.5) +
labs(
title = "Publication Day Patterns",
x = NULL,
y = "Number of Articles"
) +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
frame_dist <- clean_data %>%
count(dominant_frame, sort = TRUE) %>%
mutate(
percentage = n / sum(n) * 100,
dominant_frame = factor(dominant_frame, levels = dominant_frame)
)
ggplot(frame_dist, aes(x = reorder(dominant_frame, n), y = n, fill = dominant_frame)) +
geom_col() +
geom_text(aes(label = paste0(round(percentage, 1), "%")), hjust = -0.1, size = 3.5) +
scale_fill_manual(values = frame_colors) +
coord_flip() +
labs(
title = "Distribution of Dominant Frames",
subtitle = "Based on highest frame word count per article",
x = NULL,
y = "Number of Articles"
) +
theme(legend.position = "none") +
expand_limits(y = max(frame_dist$n) * 1.15)
frame_evolution <- monthly_stats %>%
select(year_month, prop_THREAT, prop_OPPORTUNITY, prop_REGULATION) %>%
pivot_longer(-year_month, names_to = "frame", values_to = "proportion") %>%
mutate(frame = str_remove(frame, "prop_"))
ggplot(frame_evolution, aes(x = year_month, y = proportion, color = frame)) +
geom_line(linewidth = 1.2) +
geom_point(size = 2) +
scale_color_manual(values = frame_colors) +
scale_y_continuous(labels = scales::percent) +
scale_x_date(date_breaks = "3 months", date_labels = "%b\n%Y") +
labs(
title = "Frame Prevalence Over Time",
subtitle = "Proportion of articles containing each frame",
x = NULL,
y = "Proportion of Articles",
color = "Frame"
)
frame_cols <- clean_data %>%
select(starts_with("frame_") & ends_with("_present"))
if (ncol(frame_cols) > 1) {
frame_cooccur <- crossprod(as.matrix(frame_cols))
diag_vals <- diag(frame_cooccur)
diag_vals[diag_vals == 0] <- 1
frame_cooccur_norm <- frame_cooccur / diag_vals
frame_cooccur_df <- as.data.frame(frame_cooccur_norm)
frame_cooccur_df$frame1 <- rownames(frame_cooccur_df)
frame_cooccur_df <- frame_cooccur_df %>%
pivot_longer(-frame1, names_to = "frame2", values_to = "cooccurrence") %>%
mutate(
frame1 = str_extract(frame1, "(?<=frame_)[A-Z]+"),
frame2 = str_extract(frame2, "(?<=frame_)[A-Z]+")
) %>%
filter(!is.na(frame1) & !is.na(frame2))
ggplot(frame_cooccur_df, aes(x = frame1, y = frame2, fill = cooccurrence)) +
geom_tile(color = "white") +
geom_text(aes(label = round(cooccurrence, 2)), size = 3) +
scale_fill_viridis_c(option = "magma") +
labs(
title = "Frame Co-occurrence Matrix",
subtitle = "Normalized by diagonal (self-occurrence)",
x = NULL, y = NULL, fill = "Co-occurrence"
) +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
}
phase_stats <- clean_data %>%
group_by(narrative_phase) %>%
summarise(
n = n(),
threat = mean(frame_THREAT_present, na.rm = TRUE) * 100,
opportunity = mean(frame_OPPORTUNITY_present, na.rm = TRUE) * 100,
regulation = mean(frame_REGULATION_present, na.rm = TRUE) * 100,
.groups = "drop"
) %>%
mutate(narrative_phase = factor(narrative_phase, levels = c(
"Phase 1: Emergence", "Phase 2: Debate", "Phase 3: Integration", "Phase 4: Normalization"
)))
phase_long <- phase_stats %>%
select(narrative_phase, threat, opportunity, regulation) %>%
pivot_longer(-narrative_phase, names_to = "frame", values_to = "percentage") %>%
mutate(frame = str_to_title(frame))
ggplot(phase_long, aes(x = narrative_phase, y = percentage, fill = frame)) +
geom_col(position = "dodge") +
scale_fill_manual(values = c("Threat" = "#e41a1c", "Opportunity" = "#4daf4a", "Regulation" = "#377eb8")) +
labs(
title = "Frame Distribution by Narrative Phase",
subtitle = "How dominant frames shift across coverage periods",
x = NULL,
y = "Percentage of Articles",
fill = "Frame"
) +
theme(axis.text.x = element_text(angle = 15, hjust = 1))
phase_table <- clean_data %>%
group_by(narrative_phase) %>%
summarise(
`Articles` = n(),
`Date Range` = paste(min(DATE), "—", max(DATE)),
`Mean Sentiment` = round(mean(sentiment_score, na.rm = TRUE), 2),
`% Threat Frame` = paste0(round(mean(frame_THREAT_present, na.rm = TRUE) * 100, 1), "%"),
`% Opportunity Frame` = paste0(round(mean(frame_OPPORTUNITY_present, na.rm = TRUE) * 100, 1), "%"),
.groups = "drop"
)
kable(phase_table) %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)| narrative_phase | Articles | Date Range | Mean Sentiment | % Threat Frame | % Opportunity Frame |
|---|---|---|---|---|---|
| Phase 1: Emergence | 2659 | 2021-01-01 — 2023-05-31 | 0.07 | 37.4% | 62.2% |
| Phase 2: Debate | 1050 | 2023-06-01 — 2023-12-30 | 0.31 | 36.7% | 70.4% |
| Phase 3: Integration | 164 | 2024-01-02 — 2024-07-04 | 0.28 | 30.5% | 73.2% |
ggplot(monthly_stats, aes(x = year_month)) +
geom_ribbon(aes(ymin = 0, ymax = pmax(mean_sentiment, 0)), fill = "#4daf4a", alpha = 0.5) +
geom_ribbon(aes(ymin = pmin(mean_sentiment, 0), ymax = 0), fill = "#e41a1c", alpha = 0.5) +
geom_line(aes(y = mean_sentiment), linewidth = 1.2, color = "black") +
geom_hline(yintercept = 0, linetype = "dashed") +
scale_x_date(date_breaks = "3 months", date_labels = "%b\n%Y") +
labs(
title = "Sentiment Trajectory Over Time",
subtitle = "Mean sentiment score (positive − negative word counts)",
x = NULL,
y = "Mean Sentiment Score"
)
sentiment_dist <- clean_data %>%
count(sentiment_category) %>%
mutate(percentage = n / sum(n) * 100)
ggplot(sentiment_dist, aes(x = sentiment_category, y = n, fill = sentiment_category)) +
geom_col() +
geom_text(aes(label = paste0(round(percentage, 1), "%")), vjust = -0.3, size = 4) +
scale_fill_manual(values = sentiment_colors) +
labs(
title = "Sentiment Distribution",
x = NULL,
y = "Number of Articles"
) +
theme(legend.position = "none") +
expand_limits(y = max(sentiment_dist$n) * 1.1)
actor_frequency <- clean_data %>%
summarise(
across(starts_with("actor_") & ends_with("_count"), sum),
across(starts_with("actor_") & ends_with("_present"), sum)
) %>%
pivot_longer(everything(), names_to = "metric", values_to = "value") %>%
mutate(
type = ifelse(str_detect(metric, "total_|_count"), "Total Mentions", "Articles Present"),
actor = str_extract(metric, "(?<=actor_)[A-Z_]+") %>%
str_replace_all("_", " ") %>%
str_to_title()
) %>%
filter(type == "Total Mentions") %>%
arrange(desc(value))
ggplot(actor_frequency, aes(x = reorder(actor, value), y = value)) +
geom_col(fill = "#2c7bb6", alpha = 0.8) +
coord_flip() +
labs(
title = "Actor Representation in Coverage",
subtitle = "Total mentions across all articles",
x = NULL,
y = "Total Mentions"
)
actor_frame_assoc <- clean_data %>%
filter(primary_actor != "NONE") %>%
group_by(primary_actor) %>%
summarise(
n = n(),
threat = mean(frame_THREAT_present, na.rm = TRUE) * 100,
opportunity = mean(frame_OPPORTUNITY_present, na.rm = TRUE) * 100,
regulation = mean(frame_REGULATION_present, na.rm = TRUE) * 100,
.groups = "drop"
) %>%
arrange(desc(n))
actor_frame_long <- actor_frame_assoc %>%
select(primary_actor, threat, opportunity, regulation) %>%
pivot_longer(-primary_actor, names_to = "frame", values_to = "percentage") %>%
mutate(frame = str_to_title(frame))
ggplot(actor_frame_long, aes(x = reorder(primary_actor, percentage), y = percentage, fill = frame)) +
geom_col(position = "dodge") +
scale_fill_manual(values = c("Threat" = "#e41a1c", "Opportunity" = "#4daf4a", "Regulation" = "#377eb8")) +
coord_flip() +
labs(
title = "Frame Prevalence by Primary Actor",
subtitle = "Which frames appear when each actor is prominent",
x = NULL,
y = "Percentage of Articles",
fill = "Frame"
)
# Classify outlets
outlet_classification <- tribble(
~pattern, ~outlet_type,
"24sata", "Tabloid",
"index", "Tabloid",
"jutarnji", "Quality",
"vecernji", "Quality",
"slobodna.*dalmacija", "Regional",
"novi.*list", "Regional",
"dnevnik", "Quality",
"hrt", "Public",
"n1", "Quality",
"net\\.hr", "Tabloid",
"tportal", "Quality",
"bug", "Tech",
"skolski.*portal", "Education",
"srednja", "Education",
"poslovni", "Business",
"lider", "Business"
)
clean_data$outlet_type <- "Other"
for (i in seq_len(nrow(outlet_classification))) {
matches <- str_detect(str_to_lower(clean_data$FROM), outlet_classification$pattern[i])
clean_data$outlet_type[matches] <- outlet_classification$outlet_type[i]
}outlet_type_stats <- clean_data %>%
group_by(outlet_type) %>%
summarise(
n_articles = n(),
pct_threat = mean(frame_THREAT_present, na.rm = TRUE) * 100,
pct_opportunity = mean(frame_OPPORTUNITY_present, na.rm = TRUE) * 100,
pct_regulation = mean(frame_REGULATION_present, na.rm = TRUE) * 100,
mean_sentiment = mean(sentiment_score, na.rm = TRUE),
.groups = "drop"
) %>%
arrange(desc(n_articles))
outlet_type_long <- outlet_type_stats %>%
select(outlet_type, pct_threat, pct_opportunity, pct_regulation) %>%
pivot_longer(-outlet_type, names_to = "frame", values_to = "percentage") %>%
mutate(frame = str_remove(frame, "pct_") %>% str_to_title())
ggplot(outlet_type_long, aes(x = reorder(outlet_type, percentage), y = percentage, fill = frame)) +
geom_col(position = "dodge") +
scale_fill_manual(values = c("Threat" = "#e41a1c", "Opportunity" = "#4daf4a", "Regulation" = "#377eb8")) +
coord_flip() +
labs(
title = "Frame Usage by Outlet Type",
subtitle = "How different media types frame AI in education",
x = NULL,
y = "Percentage of Articles",
fill = "Frame"
)
outlet_summary <- outlet_type_stats %>%
mutate(
`Mean Sentiment` = round(mean_sentiment, 2),
`% Threat` = paste0(round(pct_threat, 1), "%"),
`% Opportunity` = paste0(round(pct_opportunity, 1), "%"),
`% Regulation` = paste0(round(pct_regulation, 1), "%")
) %>%
select(
`Outlet Type` = outlet_type,
Articles = n_articles,
`Mean Sentiment`,
`% Threat`,
`% Opportunity`,
`% Regulation`
)
kable(outlet_summary) %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)| Outlet Type | Articles | Mean Sentiment | % Threat | % Opportunity | % Regulation |
|---|---|---|---|---|---|
| Other | 2879 | 0.17 | 35% | 61.8% | 22.9% |
| Quality | 365 | -0.12 | 46% | 78.9% | 31.8% |
| Regional | 192 | 0.26 | 44.8% | 58.9% | 23.4% |
| Tabloid | 172 | 0.23 | 31.4% | 62.2% | 23.8% |
| Education | 91 | 0.22 | 46.2% | 91.2% | 37.4% |
| Business | 76 | 0.12 | 57.9% | 90.8% | 39.5% |
| Tech | 50 | 0.32 | 26% | 88% | 30% |
| Public | 48 | -0.12 | 31.2% | 62.5% | 18.8% |
frame_outlet_table <- table(clean_data$dominant_frame, clean_data$outlet_type)
chisq_result <- chisq.test(frame_outlet_table)
cat("Chi-Square Test: Dominant Frame vs. Outlet Type\n")Chi-Square Test: Dominant Frame vs. Outlet Typecat("X² =", round(chisq_result$statistic, 2), "\n")X² = 210.9 cat("df =", chisq_result$parameter, "\n")df = 56 cat("p-value =", format(chisq_result$p.value, scientific = TRUE), "\n")p-value = 8.234689e-20 if (chisq_result$p.value < 0.05) {
cat("\nResult: Significant association between outlet type and frame usage (p < 0.05)\n")
}
Result: Significant association between outlet type and frame usage (p < 0.05)anova_result <- aov(sentiment_score ~ narrative_phase, data = clean_data)
anova_summary <- summary(anova_result)
cat("ANOVA: Sentiment Score by Narrative Phase\n")ANOVA: Sentiment Score by Narrative Phaseprint(anova_summary) Df Sum Sq Mean Sq F value Pr(>F)
narrative_phase 2 47 23.256 10.27 0.0000357 ***
Residuals 3870 8767 2.265
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1if (anova_summary[[1]]$`Pr(>F)`[1] < 0.05) {
cat("\nPost-hoc Tukey HSD:\n")
tukey_result <- TukeyHSD(anova_result)
print(tukey_result)
}
Post-hoc Tukey HSD:
Tukey multiple comparisons of means
95% family-wise confidence level
Fit: aov(formula = sentiment_score ~ narrative_phase, data = clean_data)
$narrative_phase
diff lwr upr
Phase 2: Debate-Phase 1: Emergence 0.24017336 0.11155332 0.3687934
Phase 3: Integration-Phase 1: Emergence 0.20828021 -0.07564788 0.4922083
Phase 3: Integration-Phase 2: Debate -0.03189315 -0.32818983 0.2644035
p adj
Phase 2: Debate-Phase 1: Emergence 0.0000366
Phase 3: Integration-Phase 1: Emergence 0.1978160
Phase 3: Integration-Phase 2: Debate 0.9654994The analysis reveals substantial media attention to AI in education, with identifiable peaks corresponding to key events such as ChatGPT’s release and the beginning of school semesters.
Contrary to initial expectations of moral panic, the OPPORTUNITY and REGULATION frames predominate over the THREAT frame across most of the study period. This suggests Croatian media took a relatively pragmatic approach to the topic.
Clear evidence supports the hypothesized narrative arc:
Significant differences exist between outlet types:
This analysis demonstrates that Croatian media coverage of AI in education has followed a discernible narrative arc from initial concern to pragmatic integration. While threat frames exist, they are outweighed by opportunity and regulatory framings. The findings suggest media discourse may be more nuanced than moral panic theory would predict, with significant variation across outlet types and over time.
sessionInfo()R version 4.2.2 (2022-10-31 ucrt)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 19045)
Matrix products: default
locale:
[1] LC_COLLATE=English_United States.utf8
[2] LC_CTYPE=English_United States.utf8
[3] LC_MONETARY=English_United States.utf8
[4] LC_NUMERIC=C
[5] LC_TIME=English_United States.utf8
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] progress_1.2.3 openxlsx_4.2.8
[3] broom_1.0.7 changepoint_2.2.4
[5] zoo_1.8-12 tidygraph_1.3.1
[7] ggraph_2.2.1 igraph_2.1.4
[9] kableExtra_1.4.0 knitr_1.42
[11] viridis_0.6.5 viridisLite_0.4.2
[13] RColorBrewer_1.1-3 ggrepel_0.9.6
[15] patchwork_1.3.0 scales_1.3.0
[17] ggthemes_5.1.0 ggplot2_3.5.1
[19] quanteda.textplots_0.94.4 quanteda.textstats_0.97
[21] quanteda_4.3.1 tidytext_0.4.2
[23] tibble_3.2.1 forcats_1.0.0
[25] lubridate_1.9.4 stringr_1.5.1
[27] tidyr_1.3.1 dplyr_1.1.4
loaded via a namespace (and not attached):
[1] splines_4.2.2 jsonlite_1.8.9 highr_0.11 yaml_2.3.8
[5] pillar_1.10.1 backports_1.5.0 lattice_0.20-45 glue_1.8.0
[9] digest_0.6.33 polyclip_1.10-7 colorspace_2.1-1 htmltools_0.5.7
[13] Matrix_1.5-1 pkgconfig_2.0.3 purrr_1.0.4 svglite_2.1.3
[17] tweenr_2.0.3 nsyllable_1.0.1 ggforce_0.4.2 timechange_0.3.0
[21] mgcv_1.8-41 generics_0.1.3 farver_2.1.2 cachem_1.1.0
[25] withr_3.0.2 cli_3.6.2 magrittr_2.0.3 crayon_1.5.3
[29] memoise_2.0.1 evaluate_1.0.3 stopwords_2.3 tokenizers_0.3.0
[33] janeaustenr_1.0.0 nlme_3.1-160 SnowballC_0.7.1 MASS_7.3-58.1
[37] xml2_1.3.6 prettyunits_1.2.0 tools_4.2.2 hms_1.1.3
[41] lifecycle_1.0.4 munsell_0.5.1 zip_2.3.2 compiler_4.2.2
[45] systemfonts_1.2.1 rlang_1.1.2 grid_4.2.2 rstudioapi_0.17.1
[49] htmlwidgets_1.6.4 labeling_0.4.3 rmarkdown_2.20 gtable_0.3.6
[53] graphlayouts_1.2.2 R6_2.5.1 gridExtra_2.3 fastmap_1.2.0
[57] fastmatch_1.1-6 stringi_1.8.4 Rcpp_1.0.14 vctrs_0.6.5
[61] tidyselect_1.2.1 xfun_0.37 # Export processed data for further analysis
write.xlsx(clean_data, "processed_data.xlsx")
write.xlsx(monthly_stats, "monthly_statistics.xlsx")